Assign05

I went through the sample open data sites that were included in chapter nine open data but could not find data that i could use.I went through other sites and was able to find this data at https://data.london.gov.uk/dataset/jobs-by-age-and-gender and includes a notation that it has a UK Open Government Licence.

library(tidyverse)

## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --

## v ggplot2 3.3.2     v purrr   0.3.4
## v tibble  3.0.4     v dplyr   1.0.2
## v tidyr   1.1.2     v stringr 1.4.0
## v readr   1.4.0     v forcats 0.5.0

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(readr)
jobs_by_age_and_gender <- read_csv("C:/Users/Catherine/Desktop/jobs_by_age_and_gender.csv")

## 
## -- Column specification --------------------------------------------------------
## cols(
##   date = col_character(),
##   age = col_character(),
##   gender = col_character(),
##   all_people = col_double(),
##   full_time = col_double(),
##   part_time = col_double()
## )

View(jobs_by_age_and_gender)
head(jobs_by_age_and_gender)

## # A tibble: 6 x 6
##   date              age   gender     all_people full_time part_time
##   <chr>             <chr> <chr>           <dbl>     <dbl>     <dbl>
## 1 Apr 2004-Mar 2005 16-19 All People      86900     35800     51100
## 2 Apr 2004-Mar 2005 16-19 Female          45600     16300     29300
## 3 Apr 2004-Mar 2005 16-19 Male            41300     19400     21800
## 4 Apr 2004-Mar 2005 16-64 All People    3819100   3131700    684300
## 5 Apr 2004-Mar 2005 16-64 Female        1644900   1145300    497400
## 6 Apr 2004-Mar 2005 16-64 Male          2174200   1986300    187000

Examine by gender

library(dplyr)
 
gender_groups <- jobs_by_age_and_gender %>%
  filter(gender %in% c("M", "Female"), age == "16-64", str_detect(date,"Jan."))
head(gender_groups)

## # A tibble: 6 x 6
##   date              age   gender all_people full_time part_time
##   <chr>             <chr> <chr>       <dbl>     <dbl>     <dbl>
## 1 Jan 2004-Dec 2004 16-64 Female    1641100   1129900    508700
## 2 Jan 2005-Dec 2005 16-64 Female    1672800   1161100    510700
## 3 Jan 2006-Dec 2006 16-64 Female    1701200   1190900    509800
## 4 Jan 2007-Dec 2007 16-64 Female    1718300   1191500    525200
## 5 Jan 2008-Dec 2008 16-64 Female    1778200   1229200    548600
## 6 Jan 2009-Dec 2009 16-64 Female    1797500   1221100    575000

Group_by Gender

age_groups <- jobs_by_age_and_gender %>% 
  filter(gender %in% c("Male", "Female"), str_detect(date,"Jan."), str_detect(date,".2019"), age != "16-64") %>%
  group_by(gender, age) %>%
  mutate(gender = factor(gender)) %>%
  arrange(gender) 

names(age_groups) <- c("Date", "Age Group", "Gender", "Full-time", "Part-time")
## 
## Attaching package: 'kableExtra'

## The following object is masked from 'package:dplyr':
## 
##     group_rows
head(age_groups)

## # A tibble: 6 x 6
## # Groups:   Gender, Age Group [6]
##   Date              `Age Group` Gender `Full-time` `Part-time`     NA
##   <chr>             <chr>       <fct>        <dbl>       <dbl>  <dbl>
## 1 Jan 2019-Dec 2019 16-19       Female       40100       13100  27000
## 2 Jan 2019-Dec 2019 20-24       Female      183500      126600  56900
## 3 Jan 2019-Dec 2019 25-49       Female     1513400     1099600 413400
## 4 Jan 2019-Dec 2019 50+         Female      584800      340800 243100
## 5 Jan 2019-Dec 2019 16-19       Male         30800        9200  21600
## 6 Jan 2019-Dec 2019 20-24       Male        190100      149500  40300

##Plot full time employment trends by gender of the last ten years

library(ggplot2)

  
# Plot
gender_groups %>%  tail(20) %>%
  ggplot( aes(x=date, y=full_time, group=gender, color=gender)) +
    geom_line() +
    ggtitle("Full Time Employment Trends by Gender") +
    theme_light() +
    ylab("Number Employed") + xlab("Time Period") + theme(axis.text.x = element_text(angle = 40))

##Plot Part-time employment by gender of the last ten years

options(scipen = 999) 
gender_groups %>%  tail(20) %>%
  ggplot( aes(x=date, y=part_time, group=gender, color=gender)) +
    geom_line() +
    ggtitle("Part-time Employment Trends by Gender") +
    theme_light() +
    ylab("Number Employed") + xlab ("Time Period") + theme(axis.text.x = element_text(angle = 40))